Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 31-LLAMASCOPE-RES-131K
    6. 44419
    Prev
    Next
    INDEX
    Explanations

    references to various diseases and their effects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Games
    -0.09
    neck
    -0.08
     games
    -0.08
    Games
    -0.07
    ypad
    -0.07
    laÅŁ
    -0.07
    rita
    -0.07
    ìĦłê±°
    -0.07
    озÑı
    -0.07
    aret
    -0.07
    POSITIVE LOGITS
     progression
    0.13
     process
    0.13
     processes
    0.12
    -ca
    0.11
     states
    0.11
     burden
    0.10
     state
    0.10
     outbreak
    0.10
    -state
    0.10
     entity
    0.10
    Activations Density 0.016%

    No Known Activations